Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 363 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2736. Min Act: -0.0002

Data Index: 1025071 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2792. Min Act: -0.0003

Data Index: 73324 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2711. Min Act: -0.0002

Data Index: 1238000 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2665. Min Act: -0.0002

Data Index: 143014 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2660. Min Act: -0.0003

Data Index: 1108678 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2646. Min Act: -0.0002

Data Index: 182153 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2577. Min Act: -0.0002

Data Index: 625347 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2602. Min Act: -0.0003

Data Index: 557768 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2504. Min Act: -0.0002

Data Index: 25212 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2557. Min Act: -0.0003

Data Index: 250389 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2526. Min Act: -0.0003

Data Index: 58948 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2478. Min Act: -0.0002

Data Index: 1271510 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2425. Min Act: -0.0002

Data Index: 504691 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2459. Min Act: -0.0002

Data Index: 807892 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2485. Min Act: -0.0002

Data Index: 954016 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2496. Min Act: -0.0002

Data Index: 603767 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2422. Min Act: -0.0002

Data Index: 101854 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2383. Min Act: -0.0002

Data Index: 710322 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2439. Min Act: -0.0002

Data Index: 688978 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2447. Min Act: -0.0003

Data Index: 1097402 (C4 (Web Text))

Max Activating Token Index: 16